© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84032
    Prev
    Next
    INDEX
    Explanations

    numeric values and references related to statistical or evaluative measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aign
    -0.06
    ми
    -0.06
    encer
    -0.06
    ystack
    -0.06
    pector
    -0.06
    anova
    -0.06
    ahlen
    -0.05
    insky
    -0.05
    veh
    -0.05
    rts
    -0.05
    POSITIVE LOGITS
    ,...↵↵
    0.08
    [email
    0.07
    èĢ
    0.07
    VERTISE
    0.07
    Ø´Ùħ
    0.07
    teri
    0.07
    cook
    0.07
    _require
    0.06
    *R
    0.06
    quo
    0.06
    Activations Density 0.000%

    No Known Activations